Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    say "ril/ir" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فشار
    -0.06
    _Instance
    -0.06
    358
    -0.06
    Changing
    -0.06
     Oliveira
    -0.06
     fazla
    -0.06
     κ
    -0.06
    Wildcard
    -0.06
    Ca
    -0.06
    future
    -0.06
    POSITIVE LOGITS
    (pa
    0.07
     bueno
    0.07
    alie
    0.07
    utschein
    0.07
    %p
    0.07
    illy
    0.06
    ARSE
    0.06
    umm
    0.06
    YPD
    0.06
    ียนร
    0.06
    Act Density 0.007%

    No Known Activations